TY - GEN
T1 - Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps
AU - Wang, Dingbang
AU - Zhao, Yu
AU - Feng, Sidong
AU - Zhang, Zhaoxu
AU - Halfond, William G.J.
AU - Chen, Chunyang
AU - Sun, Xiaoxia
AU - Shi, Jiangfan
AU - Yu, Tingting
N1 - Publisher Copyright:
© 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
PY - 2024/9/11
Y1 - 2024/9/11
N2 - In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.
AB - In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.
KW - Android
KW - Automated Bug Reproduction
KW - Large Language Model
KW - Prompt Engineering
UR - https://www.scopus.com/pages/publications/85205535421
U2 - 10.1145/3650212.3680341
DO - 10.1145/3650212.3680341
M3 - Conference contribution
AN - SCOPUS:85205535421
T3 - ISSTA 2024 - Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis
SP - 1048
EP - 1060
BT - ISSTA 2024 - Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis
A2 - Christakis, Maria
A2 - Pradel, Michael
PB - Association for Computing Machinery, Inc
T2 - 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2024
Y2 - 16 September 2024 through 20 September 2024
ER -